Re: objective segmenting

[Stefan Crawcour <stephen_crawcour@xxxxxxxxx>]

Dear Bernard,

thank you very much for your reply and the bibliographic references. I fully agree with your statement, when applied to spontaneous speech. But what if we are dealing with the same sentence that is read by different people ? Here the distinction between nouns and verbs should be clear. If for sentences read aloud, I decided to take the following criterion: segment sound [a] from the word [kat] , and segment at the first formant value that carries a linear difference of more than so and so many Herz from the preceding formant value, would that serve my purpose, since the formant values are different for each sound ?

Thanks,

Stephen

---

 Yahoo! FareChase - Search multiple travel sites in one click.